# MingchaoZhu/DeepLearning

Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

Repository: https://github.com/MingchaoZhu/DeepLearning
Canonical: https://ross.abutalabs.com/products/mingchaozhu-deeplearning
Language: Python
License: MIT
License Family: permissive
Topics: python, deep-learning, machine-learning, xgboost, ensemble-learning, bayesian, regularization
Last push: 2020-06-23T02:05:50+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2379, "days_push": 2263, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7744, forks 1457 (observed 2026-08-28T04:10:02.746686+00:00)

## What it is
A Chinese-language companion project to the 'Deep Learning' (flower book) textbook, re-explaining concepts via mathematical derivations and implementing them from scratch in Python with NumPy. It ships as chapter PDFs plus source-level code covering topics like regularization, ensemble learning (XGBoost, GBDT), and Bayesian methods.

## Use cases
- learn deep learning from mathematical first principles
- understand the math behind the Deep Learning book
- implement neural network algorithms from scratch in numpy
- study how xgboost and gbdt work internally
- find derivations for regularization and bayesian regression
- prepare for machine learning interviews

## When to choose
- you want source-level, framework-free implementations to deeply understand algorithms
- you prefer Chinese-language explanations with detailed derivations
- you are studying the Goodfellow Deep Learning book and need supplementary material

## When to avoid
- you need a production deep learning framework like PyTorch or TensorFlow
- you want English-language tutorials
- you need actively maintained code for current research models

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, math
- domain: deep-learning, machine-learning, tutorials, education
- platform: python
- tags: numpy, from-scratch-implementations, textbook-companion, chinese-language, xgboost, bayesian-methods, regularization

## Member repositories
- MingchaoZhu/DeepLearning (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.746686+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:35:10.111502+00:00, confidence not recorded.
  - readme: https://github.com/MingchaoZhu/DeepLearning (fetched 2026-08-28T04:10:02.746686+00:00, sha eb93d9a71a30)
- Data as of 2026-08-30T08:39:29.467469+00:00.